Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0125. Min Range: -4.0125

Max Act: 4.0125. Min Act: -0.0000

Data Index: 795750 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.9819. Min Act: -0.0000

Data Index: 160913 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.9458. Min Act: -0.0000

Data Index: 894209 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.8492. Min Act: -0.0000

Data Index: 218343 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.9665. Min Act: -0.0000

Data Index: 809239 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.7965. Min Act: -0.0000

Data Index: 1282695 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.5712. Min Act: -0.0000

Data Index: 1206740 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.5045. Min Act: -0.0000

Data Index: 544927 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.5664. Min Act: -0.0000

Data Index: 1325529 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.5028. Min Act: -0.0000

Data Index: 1061768 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.2873. Min Act: -0.0000

Data Index: 670318 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.1257. Min Act: -0.0000

Data Index: 1020180 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.1604. Min Act: -0.0000

Data Index: 519839 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.1247. Min Act: -0.0000

Data Index: 780770 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.2204. Min Act: -0.0000

Data Index: 1232510 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.1810. Min Act: -0.0000

Data Index: 39024 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.1439. Min Act: -0.0000

Data Index: 875878 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.0207. Min Act: -0.0000

Data Index: 875823 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 4.0125. Min Range: -4.0125

Max Act: 2.1149. Min Act: -0.0000

Data Index: 1586868 (Python Code)

Max Activating Token Index: 827

Text #19

Max Range: 4.0125. Min Range: -4.0125

Max Act: 1.9889. Min Act: -0.0000

Data Index: 1383612 (Python Code)

Max Activating Token Index: 501